相关论文: RNAS-CL: Robust Neural Architecture Search by Cros…

Large pretrained language models have achieved state-of-the-art results on a variety of downstream tasks. Knowledge Distillation (KD) into a smaller student model addresses their inefficiency, allowing for deployment in resource-constrained…

Prior neural architecture search (NAS) for adversarial robustness works have discovered that a lightweight and adversarially robust neural network architecture could exist in a non-robust large teacher network, generally disclosed by…

Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. Despite these high expectation, the effectiveness and…

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by jointly optimizing architecture parameters and network parameters. During the…

Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to…

Pre-trained language models achieve outstanding performance in NLP tasks. Various knowledge distillation methods have been proposed to reduce the heavy computation and storage requirements of pre-trained language models. However, from our…

Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture, nor encodes the latent…

Convolutional neural networks (CNNs) excel in computer vision but are susceptible to adversarial attacks, crafted perturbations designed to mislead predictions. Despite advances in adversarial training, a gap persists between model accuracy…

Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost…

Neural architecture search (NAS) targets at finding the optimal architecture of a neural network for a problem or a family of problems. Evaluations of neural architectures are very time-consuming. One of the possible ways to mitigate this…

Differentiable neural architecture search (DNAS) is known for its capacity in the automatic generation of superior neural networks. However, DNAS based methods suffer from memory usage explosion when the search space expands, which may…

In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity…

Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the knowledge from a given teacher model. Previous DaNAS methods…

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…

Recent advancements in deep convolutional neural networks have significantly improved the performance of saliency prediction. However, the manual configuration of the neural network architectures requires domain knowledge expertise and can…

Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges: (1) overcome the catastrophic forgetting problem, (2) adapt…

Neural architecture search (NAS) has shown great promise in automatically designing lightweight models. However, conventional approaches are insufficient in training the supernet and pay little attention to actual robot hardware resources.…

Although Deep Neural Networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs with voluminous parameters are hard to be deployed in a real-time system. To tackle this issue, Teacher-Student…

The performance of deep reinforcement learning agents is fundamentally constrained by their neural network architecture, a choice traditionally made through expensive hyperparameter searches and then fixed throughout training. This work…